From a8da474ec18f4c4c39f83202d64d73a23b755c1d Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Mon, 7 Dec 2015 10:50:51 +1100
Subject: selftests/powerpc: Add script to test HMI functionality

HMIs (Hypervisor Management|Maintenance Interrupts) are a class of interrupt
on POWER systems.

HMI support has traditionally been exceptionally difficult to test, however
Skiboot ships a tool that, with the correct magic numbers, will inject them.

This, therefore, is a first pass at a script to inject HMIs and monitor
Linux's response. It injects an HMI on each core on every chip in turn
It then watches dmesg to see if it's acknowledged by Linux.

On a Tuletta, I observed that we see 8 (or sometimes 9 or more) events per
injection, regardless of SMT setting, so we wait for 8 before progressing.

It sits in a new scripts/ directory in selftests/powerpc, because it's not
designed to be run as part of the regular make selftests process. In
particular, it is quite possibly going to end up garding lots of your CPUs,
so it should only be run if you know how to undo that.

CC: Mahesh J Salgaonkar <mahesh.salgaonkar@in.ibm.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 tools/testing/selftests/powerpc/scripts/hmi.sh | 89 ++++++++++++++++++++++++++
 1 file changed, 89 insertions(+)
 create mode 100755 tools/testing/selftests/powerpc/scripts/hmi.sh

(limited to 'tools/testing')

diff --git a/tools/testing/selftests/powerpc/scripts/hmi.sh b/tools/testing/selftests/powerpc/scripts/hmi.sh
new file mode 100755
index 0000000..83fb253
--- /dev/null
+++ b/tools/testing/selftests/powerpc/scripts/hmi.sh
@@ -0,0 +1,89 @@
+#!/bin/sh
+#
+# Copyright 2015, Daniel Axtens, IBM Corporation
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+#  the Free Software Foundation; version 2 of the License.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+
+
+# do we have ./getscom, ./putscom?
+if [ -x ./getscom ] && [ -x ./putscom ]; then
+	GETSCOM=./getscom
+	PUTSCOM=./putscom
+elif which getscom > /dev/null; then
+	GETSCOM=$(which getscom)
+	PUTSCOM=$(which putscom)
+else
+	cat <<EOF
+Can't find getscom/putscom in . or \$PATH.
+See https://github.com/open-power/skiboot.
+The tool is in external/xscom-utils
+EOF
+	exit 1
+fi
+
+# We will get 8 HMI events per injection
+# todo: deal with things being offline
+expected_hmis=8
+COUNT_HMIS() {
+    dmesg | grep -c 'Harmless Hypervisor Maintenance interrupt'
+}
+
+# massively expand snooze delay, allowing injection on all cores
+ppc64_cpu --smt-snooze-delay=1000000000
+
+# when we exit, restore it
+trap "ppc64_cpu --smt-snooze-delay=100" 0 1
+
+# for each chip+core combination
+# todo - less fragile parsing
+egrep -o 'OCC: Chip [0-9a-f]+ Core [0-9a-f]' < /sys/firmware/opal/msglog |
+while read chipcore; do
+	chip=$(echo "$chipcore"|awk '{print $3}')
+	core=$(echo "$chipcore"|awk '{print $5}')
+	fir="0x1${core}013100"
+
+	# verify that Core FIR is zero as expected
+	if [ "$($GETSCOM -c 0x${chip} $fir)" != 0 ]; then
+		echo "FIR was not zero before injection for chip $chip, core $core. Aborting!"
+		echo "Result of $GETSCOM -c 0x${chip} $fir:"
+		$GETSCOM -c 0x${chip} $fir
+		echo "If you get a -5 error, the core may be in idle state. Try stress-ng."
+		echo "Otherwise, try $PUTSCOM -c 0x${chip} $fir 0"
+		exit 1
+	fi
+
+	# keep track of the number of HMIs handled
+	old_hmis=$(COUNT_HMIS)
+
+	# do injection, adding a marker to dmesg for clarity
+	echo "Injecting HMI on core $core, chip $chip" | tee /dev/kmsg
+	# inject a RegFile recoverable error
+	if ! $PUTSCOM -c 0x${chip} $fir 2000000000000000 > /dev/null; then
+		echo "Error injecting. Aborting!"
+		exit 1
+	fi
+
+	# now we want to wait for all the HMIs to be processed
+	# we expect one per thread on the core
+	i=0;
+	new_hmis=$(COUNT_HMIS)
+	while [ $new_hmis -lt $((old_hmis + expected_hmis)) ] && [ $i -lt 12 ]; do
+	    echo "Seen $((new_hmis - old_hmis)) HMI(s) out of $expected_hmis expected, sleeping"
+	    sleep 5;
+	    i=$((i + 1))
+	    new_hmis=$(COUNT_HMIS)
+	done
+	if [ $i = 12 ]; then
+	    echo "Haven't seen expected $expected_hmis recoveries after 1 min. Aborting."
+	    exit 1
+	fi
+	echo "Processed $expected_hmis events; presumed success. Check dmesg."
+	echo ""
+done
-- 
cgit v1.1